cclsp: Skill for Claude Code

.claude/skills/security-review/SKILL.md

security-review is a skill for Claude Code from ktnyt/cclsp. It costs 44 tokens per session (509 once invoked), scanned A, original, MIT.

A security review for changes involving child processes, files, configuration files, environment variables, or language-server adapters. It checks whether untrusted input could cause unsafe commands, file access, resource use, or leftover processes.

In plain words
What is it for?
Use it to assess command injection, path traversal, symlink attacks, configuration trust, response timeouts, process cleanup, and setup-input handling.
Why use it?
These changes can let attackers run commands, read or write files outside the project, exhaust resources, or leave processes running if they are not checked carefully.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is ktnyt/cclsp's own configuration. It tells Claude Code how to work on cclsp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cclsp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ktnyt/cclsp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ktnyt/cclsp/main/.claude/skills/security-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ktnyt/cclsp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ktnyt/cclsp/security-review.svg)](https://agentmods.dev/skills/ktnyt/cclsp/security-review)
Your own site
<a href="https://agentmods.dev/skills/ktnyt/cclsp/security-review"><img src="https://agentmods.dev/badge/skills/ktnyt/cclsp/security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00509
Opus 5 $0.00022 $0.00254
Sonnet 5 $0.00009 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 8d ago against content hash bc609703c3f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

security-review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

commands) sanitized before being passed to `child_process` spawn?
.claude/skills/security-review/SKILL.md · 61 lines

What it actually says

Security Review

Invoke the security-reviewer agent to assess security-sensitive changes.

When to trigger

  • Child process spawning or lifecycle changes (src/lsp-client.ts)
  • File system read/write operations (src/file-editor.ts, src/file-scanner.ts)
  • Configuration file loading or parsing (cclsp.json, CCLSP_CONFIG_PATH)
  • Environment variable handling
  • New or modified LSP server adapter (src/lsp/adapters/)
  • Setup wizard input handling (src/setup.ts)

Review checklist

  1. Command injection: Are user-supplied values (config file paths, server commands) sanitized before being passed to child_process spawn?
  2. Path traversal: Can file paths from LSP responses escape the project root? Are file:// URIs validated before resolving?
  3. Resource exhaustion: Are there timeouts on LSP server responses? Can a malicious LSP server cause unbounded memory growth?
  4. Config trust boundary: Is cclsp.json treated as trusted input? What happens if it contains unexpected fields or types?
  5. Process cleanup: Are child processes reliably terminated on shutdown? Can orphaned processes persist?
  6. Symlink attacks: Does file resolution follow symlinks outside the project directory?

How to invoke

Use the everything-claude-code:security-reviewer agent via the Task tool:

Task(
  subagent_type: "everything-claude-code:security-reviewer",
  prompt: "Review the following changes for security concerns: <describe changes>"
)

Output expectations

The security reviewer should produce:

  • CRITICAL: Must fix before merge (injection, traversal, credential leak)
  • HIGH: Should fix before merge (missing timeouts, incomplete cleanup)
  • MEDIUM: Fix when possible (defensive checks, hardening opportunities)
  • LOW: Informational (best practice suggestions)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 61 lines · 44 tokens per session scan A bc609703c3f1

Subscribe to this mod's changes

security-review is a skill published in the GitHub repository ktnyt/cclsp (673 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 509 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

claude

Skill "claude" from paladini/locus-mcp, covering claude code skill (stub), when to use locus, when to use grep, mcp registration and status.

paladini/locus-mcp · 0 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

lsp-implement

Find all concrete implementations of an interface or abstract type. Use when you need to know what types satisfy an interface, or what subtypes exist before changing a base type.

blackwell-systems/agent-lsp · 39 tokens